{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mitigating-object-hallucinations-via-sentence","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","arxiv_id":"2507.12455","date":"2025-07-16","proceeding":null,"authors":["Shangpin Peng","Senqiao Yang","Li Jiang","Zhuotao Tian"],"abstract":"Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur prohibitive computational costs or introduce distribution mismatches between training data and model outputs. We identify a critical insight: hallucinations predominantly emerge at the early stages of text generation and propagate through subsequent outputs. To address this, we propose **SENTINEL** (**S**entence-level **E**arly i**N**tervention **T**hrough **IN**-domain pr**E**ference **L**earning), a framework that eliminates dependency on human annotations. Specifically, we first bootstrap high-quality in-domain preference pairs by iteratively sampling model outputs, validating object existence through cross-checking with two open-vocabulary detectors, and classifying sentences into hallucinated/non-hallucinated categories. Subsequently, we use context-coherent positive samples and hallucinated negative samples to build context-aware preference data iteratively. Finally, we train models using a context-aware preference loss (C-DPO) that emphasizes discriminative learning at the sentence level where hallucinations initially manifest. Experimental results show that SENTINEL can reduce hallucinations by over 90\\% compared to the original model and outperforms the previous state-of-the-art method on both hallucination benchmarks and general capabilities benchmarks, demonstrating its superiority and generalization ability. The models, datasets, and code are available at https://github.com/pspdada/SENTINEL.","url_abs":"https://arxiv.org/abs/2507.12455v1","url_pdf":"https://arxiv.org/pdf/2507.12455v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mitigating-object-hallucinations-via-sentence","repo_url":"https://github.com/pspdada/SENTINEL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":null,"task_name":"MM-Vet"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":null,"task_name":"TextVQA"}],"methods":[],"datasets_introduced":[{"slug":"sentinel","name":"SENTINEL","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2507.12455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.12455"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/pspdada/SENTINEL","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_fixture":2,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e03b180fa317c9a"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256_prefix":"55c32993da87759b","entry":"unpad_image","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/model/llava_arch.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/model/llava_arch.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55c32993da87759b"}},{"code_sha256_prefix":"ad5386da0ca6f185","entry":"load_image","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad5386da0ca6f185"}},{"code_sha256_prefix":"aadc911272bfa875","entry":"load_images","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aadc911272bfa875"}},{"code_sha256_prefix":"d964d4c8ae68d31b","entry":"resize_and_pad_image","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/mm_utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/mm_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d964d4c8ae68d31b"}},{"code_sha256_prefix":"d5904889c6fd4eb0","entry":"split_list","repo":"pspdada/SENTINEL","repo_kind":"official","path":"llava/utils.py","file_url":"https://github.com/pspdada/SENTINEL/blob/HEAD/llava/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5904889c6fd4eb0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}